A distributed control architecture for a purposive computer vision system

Author

Bianchi, Reinaldo A C ; Rillo, Anna H R C

Author_Institution

Escola Politecnica, Sao Paulo Univ., Brazil

fYear

1996

fDate

4-5 Nov 1996

Firstpage

288

Lastpage

294

Abstract

In this paper we present a distributed control architecture engaged in purposive computer vision tasks. In this context, the vision system´s purpose is translated into a set of behaviors, which are decomposed in specific tasks. A multi-agent approach is used to model purpose, behaviors, tasks and the relationship among them. Purpose is modeled by a society of autonomous agents, each one responsible for a specific visually guided behavior. Tasks are represented by basic agents, organized in a hierarchical structure with autonomous agents on the top. As a testbed, the architecture of a specific system for visually guided assembly is presented and a distributed implementation is described

Keywords

computer vision; cooperative systems; distributed processing; hierarchical systems; object recognition; planning (artificial intelligence); software agents; autonomous agents; behaviors model; distributed control architecture; hierarchical structure; multiple agent system; purpose model; purposive computer vision; robot vision; task model; visually guided assembly; Artificial intelligence; Autonomous agents; Computer architecture; Computer vision; Context modeling; Distributed control; Electronic mail; Image reconstruction; Laboratories; Machine vision;

fLanguage

English

Publisher

ieee

Conference_Titel

Intelligence and Systems, 1996., IEEE International Joint Symposia on

Conference_Location

Rockville, MD

Print_ISBN

0-8186-7728-7

Type

conf

DOI

10.1109/IJSIS.1996.565081

Filename

565081